Sensitivity & specificity are descriptive statistics that measure the quality of a classification system. They are the proportion of real positives that are classified correctly (sensitivity) & the proportion of real negatives that are classified correctly (specificity). They are an integral part of ROC analysis.
Sensitivity and specificity are descriptive statistics that measure the quality of a classification system. They are the proportion of real positives that are classified correctly (sensitivity) and the proportion of real negatives that are classified correctly (specificity). Consider the following four logical possibilities:
Reality:
Positive Negative
Classification: ---------------------------
| | |
'positive' | TP | FP |
| | |
---------------------------
| | |
'negative' | FN | TN |
| | |
---------------------------
where TP is true positive, FP is false positive, FN is false negative, and TN is true negative. Then:
\begin{align}
{\rm Sensitivity} &= \frac{TP}{TP+FN} \\[7pt]
{\rm Specificity} &= \frac{TN}{FP+TN}
\end{align}
They are often used together, and are an integral part of ROC analysis. Sensitivity and specificity are very similar to precision and recall (in fact, recall is equivalent to sensitivity).
